Abstract
With the rapid growth of internet data, knowledge graphs (KGs) are considered as efficient form of knowledge representation that captures the semantics of web objects. In recent years, reasoning over KG for various artificial intelligence tasks have received a great deal of research interest. Providing recommendations based on users’ natural language queries is an equally difficult undertaking. In this paper, we propose a novel, context-aware recommender system, based on domain KG, to respond to user-defined natural queries. The proposed recommender system consists of three stages. First, we generate incomplete triples from user queries, which are then segmented using logical conjunction (∧) and disjunction (∨) operations. Then, we generate candidates by utilizing a KGE-based framework (Query2Box) for reasoning over segmented logical triples, with ∧, ∨, and ∃ operators; finally, the generated candidates are re-ranked using neural collaborative filtering (NCF) model by exploiting contextual (auxiliary) information from GraphSAGE embedding. Our approach demonstrates to be simple, yet efficient, at providing explainable recommendations on user’s queries, while leveraging user-item contextual information. Furthermore, our framework has shown to be capable of handling logical complex queries by transforming them into a disjunctive normal form (DNF) of simple queries. In this work, we focus on the restaurant domain as an application domain and use the Yelp dataset to evaluate the system. Experiments demonstrate that the proposed recommender system generalizes well on candidate generation from logical queries and effectively re-ranks those candidates, compared to the matrix factorization model.
Highlights
Recommender systems provide personalized recommendations for a set of products or items that may be of interest to a particular user [1]
Node and edge vectors derived from knowledge graphs (KGs) embedding (KGE), where semantics of KG are preserved, are used for training and inferencing machine learning (ML) models, which is useful for analytics, deeper queries, and more accurate recommendation
Domain-specific, context-aware, explainable recommendation framework, based on a domain knowledge graph (KG) and machine learning model
Summary
Recommender systems provide personalized recommendations for a set of products or items that may be of interest to a particular user [1]. Numerous efforts have been made toward more personalized recommendations, these recommender systems remain unable to address context and other challenges, such as data sparsity and cold start problems. Recommendations based on the knowledge graph (KG) have attracted considerable interest as a source of context information. This approach alleviates the problems mentioned above for a more accurate recommendation and provides explanations for recommended items [5,6,7]. The KG is a graph representation of real-world knowledge, whose nodes represent entities and edges illustrate the semantic relation between them [8]. Finding candidate entities that satisfy queries can be approached by reasoning on KG
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
